Pilotless MIMO Spatial Multiplexing With Stream-Specific Constellations

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing deep learning-based solutions for wireless communication systems struggle with pilotless detection in multiple-input and multiple-output (MIMO) scenarios with spatial multiplexing, as they fail to effectively separate overlapping spatial streams.

Innovation Solution

Implementing an end-to-end machine learning (ML) model to generate customized constellation shapes for each transmission bit stream in a MIMO transmission, which learns transformations from predefined shapes and refines them using contextual information to enhance pilotless detection and separation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If traditional deep learning-based solutions are used for pilotless detection, then the system can operate without pilots, but it fails to effectively separate overlapping spatial streams in MIMO scenarios

Engineering Contradiction:

ImprovethroughputVSAvoiddetection accuracy

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent applies local quality by generating customized constellation shapes tailored to each specific transmission bit stream. Instead of using a single universal constellation, the system creates distinct constellation shapes for different spatial streams, enabling the receiver to properly distinguish and detect each stream independently, thus resolving the separation problem in MIMO scenarios

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The patent changes the parameter of constellation shape dynamically for each transmission bit stream. By varying the constellation shape parameters based on the specific transmission characteristics and spatial stream identifiers, the system achieves both pilotless operation and effective stream separation, improving both throughput and detection accuracy

Inventive Principle:

Principle #35Parameter changes

2Reliability

If customized constellation shapes are generated for each transmission bit stream, then pilotless detection capability is enhanced, but system complexity increases

Engineering Contradiction:

Improvepilotless detection capabilityVSAvoidconstellation generation complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by pre-defining a set of transformation matrices that map predefined constellation shapes to customized shapes. These transformations are prepared in advance and stored, allowing the system to quickly generate appropriate constellation shapes during transmission without performing complex real-time computations, thus reducing operational complexity while maintaining detection capability

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces transformation matrices as intermediary elements that bridge predefined constellation shapes and customized constellation shapes. These matrices act as mediators that encode spatial stream information and channel characteristics, simplifying the overall system architecture by breaking down the complex constellation generation process into manageable transformation steps

Inventive Principle:

Principle #24Intermediary (Mediator)

3Adaptability or versatility

If transformation matrices are used to map constellation shapes, then constellation customization is enabled, but computational requirements increase

Engineering Contradiction:

Improveconstellation customizationVSAvoidcomputational energy

Core Design Contradiction:

Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The patent applies preliminary action by pre-computing and storing transformation matrices during system initialization or training phases. During actual transmission, the system simply retrieves and applies these pre-computed matrices rather than performing complex real-time optimization, significantly reducing the computational energy required during operation while maintaining full constellation customization capability

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent applies dynamics by making the constellation shape adaptation flexible and adjustable based on transmission conditions. The system can dynamically select from pre-defined transformation matrices or adjust constellation parameters in response to changing channel conditions, enabling adaptability without requiring continuous heavy computation, thus balancing versatility with energy efficiency

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS20250392500A1Machine learning enhanced pilotless radio transmission with spatial multiplexing

Publication Date: 2025.12.25 NOKIA SOLUTIONS & NETWORKS OY

AI summary

Machine learning enhanced pilotless radio transmission with spatial multiplexing is disclosed. Parallel transmission bit streams are obtained at a radio transmitter device. The radio transmitter device modulates the obtained parallel transmission bit streams for a pilotless multiple-input and multiple-output (MIMO) transmission over a radio channel based on transmission bit stream-specific customized constellation shapes. The customized constellation shapes are generated with an end-to-end machine learning (ML) model representing the radio transmitter device, a radio receiver device and the radio channel. The end-to-end ML model is executable to learn a separate customized constellation shape for each of the at least two parallel transmission bit streams.